Run 4. Outer Step 14. Inner Step 35.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5512622,
-    5512626,
-    5512630,
-    5512634,
-    5512637,
-    5512641
+    5512646,
+    5512650,
+    5512654,
+    5512658,
+    5512662,
+    5512666
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 34,
+  "inner_step": 35,
   "inner_steps": 0,
   "last_allreduce_block": 5511564,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d5f6e9a807c2b4ef3fb67777a2c461b4f977dea5efd2293494c4d00158ce322
+oid sha256:55861fe1aa2d9dd61e704687a46825751b1fc95b7a17baa889a000a01c4739c9
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d6b21a2530594b3ce0ff33971f16225de81119b497c1a65bf23a0e79fb28b89
+oid sha256:3ac91c8d3aa907514cbf307030551cadce6f9d415c7bf2f916d68754a943ce5f
 size 4040701744